-
Notifications
You must be signed in to change notification settings - Fork 680
Pull requests: PaddlePaddle/FastDeploy
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
[Cherry-Pick][BugFix] Support redundant expert for eplb (#5918)
#5923
opened Jan 7, 2026 by
xiaoxiaohehe001
Loading…
5 tasks done
[Cherry-Pick] [BugFix] fix mtp split kv attetion
#5921
opened Jan 7, 2026 by
lizhenyun01
Loading…
5 tasks
[Cherry-Pick][Optimization] Support setting communication groups in custom_allreduce and the all-to-all\transpose fused operator during the decoding phase. #5917
#5919
opened Jan 7, 2026 by
carryyu
Loading…
5 tasks
[BugFix] Support redundant expert for eplb
#5918
opened Jan 7, 2026 by
xiaoxiaohehe001
Loading…
5 tasks done
[Optimization] Support setting communication groups in custom_allreduce and the all-to-all\transpose fused operator during the decoding phase.
#5917
opened Jan 7, 2026 by
carryyu
Loading…
5 tasks
[Models] Add Qwen3-VL Moe Model Support
#5913
opened Jan 6, 2026 by
CSWYF3634076
Loading…
5 tasks done
[FDConfig] add flashinfer-python-paddle depend
#5912
opened Jan 6, 2026 by
BingooYang
Loading…
5 tasks done
[INTEL HPU] support only one release package of PaddleCustomDevice
contributor
External developers
#5910
opened Jan 6, 2026 by
FocusLuo
Loading…
2 of 5 tasks
[Cherry Pick][XPU][CI] Add logprobs Case
contributor
External developers
#5907
opened Jan 6, 2026 by
plusNew001
Loading…
5 tasks
[Bug fix][Cherry-pick] Limit multi-modal request for prefill batch to 1(#5901)
#5902
opened Jan 6, 2026 by
rainyfly
Loading…
5 tasks
[Bug fix] Limit multi-modal request for prefill batch to 1
#5901
opened Jan 6, 2026 by
rainyfly
Loading…
5 tasks
[Cherry-Pick][CI]Support multi-step mtp with cudagraph(#5886)
#5898
opened Jan 6, 2026 by
freeliuzc
Loading…
5 tasks
[Cherry-Pick][CI]Support multi-step mtp with cudagraph(#5886)
#5897
opened Jan 6, 2026 by
freeliuzc
Loading…
5 tasks
[INTEL_HPU] supported ERNIE-4.5-21B-A3B-Thinking mold
contributor
External developers
#5891
opened Jan 6, 2026 by
FocusLuo
Loading…
3 of 5 tasks
[Feature] Add Golang-based Router for Request Scheduling and Load Balancing
contributor
External developers
#5882
opened Jan 5, 2026 by
mouxinqq
Loading…
5 tasks
[BugFix][Cherry-Pick] Cp fix eb5 prefix cache(#5879)
#5881
opened Jan 5, 2026 by
kevincheng2
Loading…
5 tasks
[Optimization] Accelerate Qwen3 QK RMSNorm via Fused Triton Kernel
#5880
opened Jan 5, 2026 by
Sunny-bot1
Loading…
5 tasks done
[XPU] move xpu_attn_backend.py to FastDeploy/fastdeploy/model_executor/layers/backends/xpu
#5878
opened Jan 5, 2026 by
zccjjj
Loading…
5 tasks
[Intel HPU] enable MoE EP for hpu
contributor
External developers
#5855
opened Jan 4, 2026 by
yanfeich
Loading…
2 tasks
[Cherry-Pick][Feature] support rl_tp_degree(#5850)
#5851
opened Dec 31, 2025 by
lizhenyun01
Loading…
5 tasks
Previous Next
ProTip!
no:milestone will show everything without a milestone.